Reliability, Availability, And Serviceability Features - IBM BladeCenter HX5 Installation And User Manual

v Light path diagnostics
v PCI Express
v Power throttling

Reliability, availability, and serviceability features

Three of the most important features in server design are reliability, availability,
and serviceability (RAS). These RAS features help to ensure the integrity of the
data that is stored in the blade server, the availability of the blade server when you
need it, and the ease with which you can diagnose and correct problems.
The blade server has the following RAS features:
v Customer upgrade of flash ROM-resident code and diagnostics
v Power policy 24-hour support center
v Vital product data (VPD) on memory
v Processor presence detection
v Advanced Configuration and Power Interface (ACPI)
v Automatic server restart (ASR)
v Built-in diagnostics using DSA Preboot, which is stored in integrated USB
v Built in monitoring for temperature, voltage, and hard disk drives
10
IBM BladeCenter HX5 Type 7873, 7872, 1910, and 1909: Installation and User's Guide
Combining two blade servers into a scalable blade complex provides you with
implementation flexibility through FlexNode partitioning. Through the advanced
management module, you can implement the scalable blade complex as a single
server or as two independent servers without changing the physical setup of the
blade servers. For more information about scalable blade complexes and
FlexNode partitioning, see "Working with a scalable blade complex" on page 13.
Light path diagnostics provides light-emitting diodes (LEDs) to help you
diagnose problems. For more information, see the Problem Determination and
Service Guide.
In addition, scalability indicators are available through the front bezel. These
indicators enable you to tell whether BladeCenter HX5 blade servers are
operating independently or as a single hardware partition.
PCI Express is a serial interface that is used for chip-to-chip interconnect and
expansion adapter interconnect. With the blade expansion connector, you can
add optional I/O and storage devices.
Each blade server is powered by two Enterprise Voltage Regulator-Down
(EVRD) 11.0 voltage regulators. By enforcing a power policy known as
power-domain oversubscription, the BladeCenter chassis can share the power
load between two power modules to ensure sufficient power for each device in
the BladeCenter chassis. This policy is enforced when the initial power is
applied to the BladeCenter chassis or when a blade server is inserted into the
BladeCenter chassis.
The following settings for this policy are available:
– Power module redundancy
– Power module redundancy with blade throttling allowed
– Basic power management
You can configure and monitor the power environment by using the advanced
management module. For more information about configuring and using power
throttling, see the Advanced Management Module User's Guide (available at
http://publib.boulder.ibm.com/infocenter/bladectr/documentation/index.jsp)
or http://www.ibm.com/systems/support/.
memory.